Support Knowledge Base

Why Can Caffe Models Be Used Directly with OpenVINO™ Toolkit Inference Engine API?

Content Type: Compatibility | Article ID: 000088387 | Last Reviewed: 05/20/2022

Description Resolution

Description

Inferenced Caffe model directly on Intel® Neural Compute Stick 2 (Intel® NCS2).
Unable to determine why Caffe model can be used directly with OpenVINO™ Toolkit Inference Engine API without converting to Intermediate Representation (IR).

Resolution

Only limited Caffe frameworks can be used directly with the OpenVINO™ Toolkit Inference Engine API.

Currently, the frameworks supported by OpenVINO™ Toolkit Inference Engine API are:

Intermediate Representation (IR)
ONNX

Related Products

This article applies to 4 products.

Intel® Xeon Phi™ Processor Software OpenVINO™ toolkit Performance Libraries

Discontinued Products

Intel® Developer Cloud for the Edge

Need more help?

Contact support

Contact support